Restates the previous response in plain language, with no jargon. Use when the user says "bro", asks to "say that plainly", says "explain it simply", or invokes $prp-bro.

This skill should be used when the user asks to "create stacked PR", "stack PRs", "dependent PR", "rebase stack", "merge stack", or manage PR dependencies. Uses GitHub's native stacked pull request workflow for dependent changes split across multiple pull requests.

This skill should be used when the user asks to "open a PR", "prepare for review", "address review comments", "run gates", or "verify before pushing" in this repository. Enforces preflight/gate workflow, migration safety, and review-evidence closure.

Run a full review of all Architecture Decision Records for implementation drift, contradictions, stale decisions, missing supersession notes, weak rationale, and missing cross-references. Use when the user asks for an ADR review, ADR audit, stale ADR check, architecture decision consistency check, or wants to verify ADRs against the current codebase, feature/design records, architecture docs, glossary, or public API state.

Screenshot capture for deterministic PNG evidence and visual-contract bundles for Compozy Storybook stories and local UI URLs. Use for visual audits, regression diffs, and design-parity checks. Do not use for interactive E2E flows, remote authenticated sites, or Storybook test execution.

Create and edit Bento presentations — single-file .bento.html decks whose document is plain JSON in a "#bento-doc" script block. Use whenever the user wants a slide deck or presentation: starting from NOTHING (it downloads the latest Bento app from bento.page automatically), from source material, or by improving an existing .bento.html. Maps content to the right feature (charts, morph transitions, state slides, ken-burns, motion paths) instead of static text slides, then writes the document JSON in place. Full schema + recipes at https://bento.page/agents.md.

Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Use when strategy_drafts/*.yaml exists and needs quality gate before pipeline export. Outputs PASS/REVISE/REJECT verdicts with confidence scores.

BK-CI 发版 Changelog 增量处理：仅针对本次新增版本块生成「变更概述」并写回中文文件， 再将该增量版本翻译到英文 CHANGELOG。当用户提到发版摘要、变更概述、CHANGELOG 翻译、 中英文 changelog、vX.Y.Z-rc、补充概述、同步英文日志时使用。

Consult official Claude Code documentation from code.claude.com using selective fetching. Use when working on hooks, skills, subagents, plugins, agent teams, MCP servers, permissions, settings, CI/CD (GitHub Actions, GitLab), IDE extensions (VS Code, JetBrains), desktop/web app features, scheduling, memory/CLAUDE.md, deployment (Bedrock, Vertex, Foundry), sandboxing, monitoring, or any Claude Code feature requiring official docs. Fetches only the specific docs needed per task.

Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.

Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity.

Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.

Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable or undesired. Returns a small set of relevant results (title, url, snippet) and can optionally include short answer summaries.

Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation history, token usage, cost accounting, execution log, or artifact metadata beyond what host.frames()/host.artifacts() provide — e.g. "how many tokens has this session used", "what was my last tool call", "list every file I've written", "where are messages stored", "what tables can I query", "inspect frames.context_data", or any time you're about to PRAGMA-probe the Claude Science metadata DB to discover its schema.

This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables.

Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.

Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. Use when the user asks to "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model".

Cache and refresh remote git repositories under ~/.cache/checkouts/<host>/<org>/<repo> so future references can reuse a local copy. Use this skill when the user points you to a remote git repository as reference or you encountered a remote git repo through other means.